linux-kernel - Re: [PATCH bpf-next 1/3] perf/core: Prepare sample data before calling BPF

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Tue, 1 Nov 2022 11:03:19 +0100
From:   Jiri Olsa <olsajiri@...il.com>
To:     Namhyung Kim <namhyung@...nel.org>
Cc:     Alexei Starovoitov <ast@...nel.org>,
        Daniel Borkmann <daniel@...earbox.net>,
        Andrii Nakryiko <andrii@...nel.org>,
        Song Liu <songliubraving@...com>,
        Peter Zijlstra <peterz@...radead.org>,
        Martin KaFai Lau <kafai@...com>, Yonghong Song <yhs@...com>,
        John Fastabend <john.fastabend@...il.com>,
        KP Singh <kpsingh@...nel.org>, Hao Luo <haoluo@...gle.com>,
        Stanislav Fomichev <sdf@...gle.com>,
        LKML <linux-kernel@...r.kernel.org>, bpf@...r.kernel.org,
        Steven Rostedt <rostedt@...dmis.org>,
        Ingo Molnar <mingo@...nel.org>,
        Arnaldo Carvalho de Melo <acme@...nel.org>
Subject: Re: [PATCH bpf-next 1/3] perf/core: Prepare sample data before
 calling BPF

On Mon, Oct 31, 2022 at 10:23:38PM -0700, Namhyung Kim wrote:
> To allow bpf overflow handler to access the perf sample data, it needs to
> prepare missing but requested data before calling the handler.
> 
> I'm taking a conservative approach to allow a list of sample formats only
> instead of allowing them all.  For now, IP and ADDR data are allowed and
> I think it's good enough to build and verify general BPF-based sample
> filters for perf events.
> 
> Signed-off-by: Namhyung Kim <namhyung@...nel.org>
> ---
>  kernel/events/core.c | 40 +++++++++++++++++++++++++++++++---------
>  1 file changed, 31 insertions(+), 9 deletions(-)
> 
> diff --git a/kernel/events/core.c b/kernel/events/core.c
> index aefc1e08e015..519f30c33a24 100644
> --- a/kernel/events/core.c
> +++ b/kernel/events/core.c
> @@ -7329,8 +7329,10 @@ void perf_prepare_sample(struct perf_event_header *header,
>  	filtered_sample_type = sample_type & ~data->sample_flags;
>  	__perf_event_header__init_id(header, data, event, filtered_sample_type);
>  
> -	if (sample_type & (PERF_SAMPLE_IP | PERF_SAMPLE_CODE_PAGE_SIZE))
> -		data->ip = perf_instruction_pointer(regs);
> +	if (sample_type & (PERF_SAMPLE_IP | PERF_SAMPLE_CODE_PAGE_SIZE)) {
> +		if (filtered_sample_type & PERF_SAMPLE_IP)
> +			data->ip = perf_instruction_pointer(regs);
> +	}
>  
>  	if (sample_type & PERF_SAMPLE_CALLCHAIN) {
>  		int size = 1;
> @@ -10006,6 +10008,32 @@ static void perf_event_free_filter(struct perf_event *event)
>  }
>  
>  #ifdef CONFIG_BPF_SYSCALL
> +static void bpf_prepare_sample(struct bpf_prog *prog,
> +			       struct perf_event *event,
> +			       struct perf_sample_data *data,
> +			       struct pt_regs *regs)
> +{
> +	u64 filtered_sample_type;
> +
> +	filtered_sample_type = event->attr.sample_type & ~data->sample_flags;

could we add the same comment in here as is in perf_prepare_sample

        /*
         * Clear the sample flags that have already been done by the
         * PMU driver.
         */

it took me while to recall while we set addr to 0 in here ;-)

thanks,
jirka

> +
> +	if (prog->call_get_stack &&
> +	    (filtered_sample_type & PERF_SAMPLE_CALLCHAIN)) {
> +		data->callchain = perf_callchain(event, regs);
> +		data->sample_flags |= PERF_SAMPLE_CALLCHAIN;
> +	}
> +
> +	if (filtered_sample_type & PERF_SAMPLE_IP) {
> +		data->ip = perf_instruction_pointer(regs);
> +		data->sample_flags |= PERF_SAMPLE_IP;
> +	}
> +
> +	if (filtered_sample_type & PERF_SAMPLE_ADDR) {
> +		data->addr = 0;
> +		data->sample_flags |= PERF_SAMPLE_ADDR;
> +	}
> +}
> +
>  static void bpf_overflow_handler(struct perf_event *event,
>  				 struct perf_sample_data *data,
>  				 struct pt_regs *regs)
> @@ -10023,13 +10051,7 @@ static void bpf_overflow_handler(struct perf_event *event,
>  	rcu_read_lock();
>  	prog = READ_ONCE(event->prog);
>  	if (prog) {
> -		if (prog->call_get_stack &&
> -		    (event->attr.sample_type & PERF_SAMPLE_CALLCHAIN) &&
> -		    !(data->sample_flags & PERF_SAMPLE_CALLCHAIN)) {
> -			data->callchain = perf_callchain(event, regs);
> -			data->sample_flags |= PERF_SAMPLE_CALLCHAIN;
> -		}
> -
> +		bpf_prepare_sample(prog, event, data, regs);
>  		ret = bpf_prog_run(prog, &ctx);
>  	}
>  	rcu_read_unlock();
> -- 
> 2.38.1.273.g43a17bfeac-goog
>